RAW-Explainer: Post-hoc Explanations of Graph Neural Networks on Knowledge Graphs
This addresses the challenge of explainability in GNNs for knowledge graph tasks, which is important for users needing interpretable AI decisions, though it is incremental as it builds on existing methods for heterogeneous settings.
The paper tackles the problem of interpreting graph neural network predictions for link prediction in knowledge graphs by proposing RAW-Explainer, a framework that generates connected and concise subgraph explanations, achieving a balance between explanation quality and computational efficiency with significant speed improvements.
Graph neural networks have demonstrated state-of-the-art performance on knowledge graph tasks such as link prediction. However, interpreting GNN predictions remains a challenging open problem. While many GNN explainability methods have been proposed for node or graph-level tasks, approaches for generating explanations for link predictions in heterogeneous settings are limited. In this paper, we propose RAW-Explainer, a novel framework designed to generate connected, concise, and thus interpretable subgraph explanations for link prediction. Our method leverages the heterogeneous information in knowledge graphs to identify connected subgraphs that serve as patterns of factual explanation via a random walk objective. Unlike existing methods tailored to knowledge graphs, our approach employs a neural network to parameterize the explanation generation process, which significantly speeds up the production of collective explanations. Furthermore, RAW-Explainer is designed to overcome the distribution shift issue when evaluating the quality of an explanatory subgraph which is orders of magnitude smaller than the full graph, by proposing a robust evaluator that generalizes to the subgraph distribution. Extensive quantitative results on real-world knowledge graph datasets demonstrate that our approach strikes a balance between explanation quality and computational efficiency.